Novel Approaches for Exclusive and Continuous Fingerprint Classification
This paper proposes novel exclusive and continuous approaches to guide the search and the retrieval in fingerprint image databases. Both approaches are useful to perform a coarse level classification of fingerprint images before fingerprint authentication tasks. Our approaches are characterized by: (1) texture image descriptors based on pairs of multi-resolution decomposition methods that encode effectively global and local fingerprint information, with similarity measures used for fingerprint matching purposes, and (2) a novel multi-class object recognition method based on the Optimum Path Forest classifier. Experiments were carried out on the standard NIST-4 dataset aiming to study the discriminative and scalability capabilities of our approaches. The high classification rates allow us demonstrate the feasibility and validity of our approaches for characterizing fingerprint images accurately.
KeywordsFeature Vector Optimum Path Minimum Span Tree Query Image Image Descriptor
- 12.Cousty, J., Bertrand, G., Najman, L., Couprie, M.: Watersheds, minimum spanning forests, and the drop of water principle, École Supérieure d’Ingénieurs (2007)Google Scholar
- 13.Papa, J., Falcão, A.: A new variant of the optimum-path forest classifier. In: 4th International Symposium on Visual Computing (accepted, 2008)Google Scholar
- 14.Watson, C., Wilson, C.: Nist special database 4, fingerprint database. U.S. National Institute of Standards and Technology (1992)Google Scholar